From 331b72922c5f58d48fd5500acadc91777cc31970 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Fri, 12 Sep 2014 20:08:20 -0700 Subject: net: sched: RCU cls_tcindex Make cls_tcindex RCU safe. This patch addds a new RCU routine rcu_dereference_bh_rtnl() to check caller either holds the rcu read lock or RTNL. This is needed to handle the case where tcindex_lookup() is being called in both cases. Signed-off-by: John Fastabend Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux/rtnetlink.h') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 167bae7bdfa4..6cacbce1a06c 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -46,6 +46,16 @@ static inline int lockdep_rtnl_is_held(void) #define rcu_dereference_rtnl(p) \ rcu_dereference_check(p, lockdep_rtnl_is_held()) +/** + * rcu_dereference_bh_rtnl - rcu_dereference_bh with debug checking + * @p: The pointer to read, prior to dereference + * + * Do an rcu_dereference_bh(p), but check caller either holds rcu_read_lock_bh() + * or RTNL. Note : Please prefer rtnl_dereference() or rcu_dereference_bh() + */ +#define rcu_dereference_bh_rtnl(p) \ + rcu_dereference_bh_check(p, lockdep_rtnl_is_held()) + /** * rtnl_dereference - fetch RCU pointer when updates are prevented by RTNL * @p: The pointer to read, prior to dereferencing -- cgit v1.2.3 From f6f6424ba773da6221ecaaa70973eb4dacfa03b2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 28 Nov 2014 14:34:15 +0100 Subject: net: make vid as a parameter for ndo_fdb_add/ndo_fdb_del Do the work of parsing NDA_VLAN directly in rtnetlink code, pass simple u16 vid to drivers from there. Signed-off-by: Jiri Pirko Acked-by: Andy Gospodarek Acked-by: Jamal Hadi Salim Acked-by: John Fastabend Signed-off-by: David S. Miller --- drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 +- drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c | 9 +++-- drivers/net/macvlan.c | 4 +- drivers/net/vxlan.c | 4 +- include/linux/netdevice.h | 8 ++-- include/linux/rtnetlink.h | 6 ++- net/bridge/br_fdb.c | 39 ++---------------- net/bridge/br_private.h | 4 +- net/core/rtnetlink.c | 50 ++++++++++++++++++++---- 10 files changed, 70 insertions(+), 60 deletions(-) (limited to 'include/linux/rtnetlink.h') diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 7262077ad547..5ed5e4036dd9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7536,7 +7536,7 @@ static int i40e_get_phys_port_id(struct net_device *netdev, */ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr, + const unsigned char *addr, u16 vid, u16 flags) { struct i40e_netdev_priv *np = netdev_priv(dev); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 52776f9e1f71..74aadeb56ada 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7708,7 +7708,7 @@ static int ixgbe_set_features(struct net_device *netdev, static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr, + const unsigned char *addr, u16 vid, u16 flags) { /* guarantee we can provide a unique filter for the unicast address */ @@ -7717,7 +7717,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return -ENOMEM; } - return ndo_dflt_fdb_add(ndm, tb, dev, addr, flags); + return ndo_dflt_fdb_add(ndm, tb, dev, addr, vid, flags); } static int ixgbe_ndo_bridge_setlink(struct net_device *dev, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index a913b3ad2f89..3227c8063edd 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -376,13 +376,14 @@ static int qlcnic_set_mac(struct net_device *netdev, void *p) } static int qlcnic_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *netdev, const unsigned char *addr) + struct net_device *netdev, + const unsigned char *addr, u16 vid) { struct qlcnic_adapter *adapter = netdev_priv(netdev); int err = -EOPNOTSUPP; if (!adapter->fdb_mac_learn) - return ndo_dflt_fdb_del(ndm, tb, netdev, addr); + return ndo_dflt_fdb_del(ndm, tb, netdev, addr, vid); if ((adapter->flags & QLCNIC_ESWITCH_ENABLED) || qlcnic_sriov_check(adapter)) { @@ -401,13 +402,13 @@ static int qlcnic_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], static int qlcnic_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *netdev, - const unsigned char *addr, u16 flags) + const unsigned char *addr, u16 vid, u16 flags) { struct qlcnic_adapter *adapter = netdev_priv(netdev); int err = 0; if (!adapter->fdb_mac_learn) - return ndo_dflt_fdb_add(ndm, tb, netdev, addr, flags); + return ndo_dflt_fdb_add(ndm, tb, netdev, addr, vid, flags); if (!(adapter->flags & QLCNIC_ESWITCH_ENABLED) && !qlcnic_sriov_check(adapter)) { diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 11d4b3506d6e..9538674587aa 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -873,7 +873,7 @@ static int macvlan_vlan_rx_kill_vid(struct net_device *dev, static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr, + const unsigned char *addr, u16 vid, u16 flags) { struct macvlan_dev *vlan = netdev_priv(dev); @@ -898,7 +898,7 @@ static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], static int macvlan_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr) + const unsigned char *addr, u16 vid) { struct macvlan_dev *vlan = netdev_priv(dev); int err = -EINVAL; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index d802a1ae4560..31ecb03368c6 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -849,7 +849,7 @@ static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan, /* Add static entry (via netlink) */ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr, u16 flags) + const unsigned char *addr, u16 vid, u16 flags) { struct vxlan_dev *vxlan = netdev_priv(dev); /* struct net *net = dev_net(vxlan->dev); */ @@ -885,7 +885,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], /* Delete entry (via netlink) */ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr) + const unsigned char *addr, u16 vid) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2cb772495f7a..589929cf4700 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -951,11 +951,11 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, - * const unsigned char *addr, u16 flags) + * const unsigned char *addr, u16 vid, u16 flags) * Adds an FDB entry to dev for addr. * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, - * const unsigned char *addr) + * const unsigned char *addr, u16 vid) * Deletes the FDB entry from dev coresponding to addr. * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, * struct net_device *dev, struct net_device *filter_dev, @@ -1128,11 +1128,13 @@ struct net_device_ops { struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, + u16 vid, u16 flags); int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr); + const unsigned char *addr, + u16 vid); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 6cacbce1a06c..063f0f581fe0 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -94,11 +94,13 @@ extern int ndo_dflt_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, - u16 flags); + u16 vid, + u16 flags); extern int ndo_dflt_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr); + const unsigned char *addr, + u16 vid); extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u16 mode); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 08ef4e7a2439..b1be971eb06c 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -805,33 +805,17 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p, /* Add new permanent fdb entry with RTM_NEWNEIGH */ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr, u16 nlh_flags) + const unsigned char *addr, u16 vid, u16 nlh_flags) { struct net_bridge_port *p; int err = 0; struct net_port_vlans *pv; - unsigned short vid = VLAN_N_VID; if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) { pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); return -EINVAL; } - if (tb[NDA_VLAN]) { - if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) { - pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n"); - return -EINVAL; - } - - vid = nla_get_u16(tb[NDA_VLAN]); - - if (!vid || vid >= VLAN_VID_MASK) { - pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", - vid); - return -EINVAL; - } - } - if (is_zero_ether_addr(addr)) { pr_info("bridge: RTM_NEWNEIGH with invalid ether address\n"); return -EINVAL; @@ -845,7 +829,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], } pv = nbp_get_vlan_info(p); - if (vid != VLAN_N_VID) { + if (vid) { if (!pv || !test_bit(vid, pv->vlan_bitmap)) { pr_info("bridge: RTM_NEWNEIGH with unconfigured " "vlan %d on port %s\n", vid, dev->name); @@ -903,27 +887,12 @@ static int __br_fdb_delete(struct net_bridge_port *p, /* Remove neighbor entry with RTM_DELNEIGH */ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr) + const unsigned char *addr, u16 vid) { struct net_bridge_port *p; int err; struct net_port_vlans *pv; - unsigned short vid = VLAN_N_VID; - - if (tb[NDA_VLAN]) { - if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) { - pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n"); - return -EINVAL; - } - vid = nla_get_u16(tb[NDA_VLAN]); - - if (!vid || vid >= VLAN_VID_MASK) { - pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", - vid); - return -EINVAL; - } - } p = br_port_get_rtnl(dev); if (p == NULL) { pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n", @@ -932,7 +901,7 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], } pv = nbp_get_vlan_info(p); - if (vid != VLAN_N_VID) { + if (vid) { if (!pv || !test_bit(vid, pv->vlan_bitmap)) { pr_info("bridge: RTM_DELNEIGH with unconfigured " "vlan %d on port %s\n", vid, dev->name); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 5b370773ad9c..1b529da8234d 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -404,9 +404,9 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid, bool added_by_user); int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, const unsigned char *addr); + struct net_device *dev, const unsigned char *addr, u16 vid); int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr, u16 nlh_flags); + const unsigned char *addr, u16 vid, u16 nlh_flags); int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *fdev, int idx); int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b9b7dfaf202b..1a233c1c8ab4 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include @@ -2312,7 +2313,7 @@ errout: int ndo_dflt_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr, + const unsigned char *addr, u16 vid, u16 flags) { int err = -EINVAL; @@ -2338,6 +2339,28 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm, } EXPORT_SYMBOL(ndo_dflt_fdb_add); +static int fdb_vid_parse(struct nlattr *vlan_attr, u16 *p_vid) +{ + u16 vid = 0; + + if (vlan_attr) { + if (nla_len(vlan_attr) != sizeof(u16)) { + pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan\n"); + return -EINVAL; + } + + vid = nla_get_u16(vlan_attr); + + if (!vid || vid >= VLAN_VID_MASK) { + pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid vlan id %d\n", + vid); + return -EINVAL; + } + } + *p_vid = vid; + return 0; +} + static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); @@ -2345,6 +2368,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) struct nlattr *tb[NDA_MAX+1]; struct net_device *dev; u8 *addr; + u16 vid; int err; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); @@ -2370,6 +2394,10 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) addr = nla_data(tb[NDA_LLADDR]); + err = fdb_vid_parse(tb[NDA_VLAN], &vid); + if (err) + return err; + err = -EOPNOTSUPP; /* Support fdb on master device the net/bridge default case */ @@ -2378,7 +2406,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) struct net_device *br_dev = netdev_master_upper_dev_get(dev); const struct net_device_ops *ops = br_dev->netdev_ops; - err = ops->ndo_fdb_add(ndm, tb, dev, addr, nlh->nlmsg_flags); + err = ops->ndo_fdb_add(ndm, tb, dev, addr, vid, + nlh->nlmsg_flags); if (err) goto out; else @@ -2389,9 +2418,10 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) if ((ndm->ndm_flags & NTF_SELF)) { if (dev->netdev_ops->ndo_fdb_add) err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr, + vid, nlh->nlmsg_flags); else - err = ndo_dflt_fdb_add(ndm, tb, dev, addr, + err = ndo_dflt_fdb_add(ndm, tb, dev, addr, vid, nlh->nlmsg_flags); if (!err) { @@ -2409,7 +2439,7 @@ out: int ndo_dflt_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr) + const unsigned char *addr, u16 vid) { int err = -EINVAL; @@ -2438,6 +2468,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) struct net_device *dev; int err = -EINVAL; __u8 *addr; + u16 vid; if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; @@ -2465,6 +2496,10 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) addr = nla_data(tb[NDA_LLADDR]); + err = fdb_vid_parse(tb[NDA_VLAN], &vid); + if (err) + return err; + err = -EOPNOTSUPP; /* Support fdb on master device the net/bridge default case */ @@ -2474,7 +2509,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) const struct net_device_ops *ops = br_dev->netdev_ops; if (ops->ndo_fdb_del) - err = ops->ndo_fdb_del(ndm, tb, dev, addr); + err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid); if (err) goto out; @@ -2485,9 +2520,10 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) /* Embedded bridge, macvlan, and any other device support */ if (ndm->ndm_flags & NTF_SELF) { if (dev->netdev_ops->ndo_fdb_del) - err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr); + err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr, + vid); else - err = ndo_dflt_fdb_del(ndm, tb, dev, addr); + err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid); if (!err) { rtnl_fdb_notify(dev, addr, RTM_DELNEIGH); -- cgit v1.2.3 From 2c3c031c8f8930861815fa1685d7c5e8ccec047c Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Fri, 28 Nov 2014 14:34:25 +0100 Subject: bridge: add brport flags to dflt bridge_getlink To allow brport device to return current brport flags set on port. Add returned flags to nested IFLA_PROTINFO netlink msg built in dflt getlink. With this change, netlink msg returned for bridge_getlink contains the port's offloaded flag settings (the port's SELF settings). Signed-off-by: Scott Feldman Signed-off-by: Jiri Pirko Acked-by: Andy Gospodarek Acked-by: Thomas Graf Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 3 ++- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- include/linux/rtnetlink.h | 3 ++- net/core/rtnetlink.c | 39 ++++++++++++++++++++++++++- 4 files changed, 43 insertions(+), 4 deletions(-) (limited to 'include/linux/rtnetlink.h') diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index dc77ec2bdafd..e0ab7673afe7 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4367,7 +4367,8 @@ static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, return ndo_dflt_bridge_getlink(skb, pid, seq, dev, hsw_mode == PORT_FWD_TYPE_VEPA ? - BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB); + BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB, + 0, 0); } #ifdef CONFIG_BE2NET_VXLAN diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 74aadeb56ada..9afa167d52a6 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7778,7 +7778,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, else mode = BRIDGE_MODE_VEPA; - return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode); + return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode, 0, 0); } static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev) diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 063f0f581fe0..3b0419072f88 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -103,5 +103,6 @@ extern int ndo_dflt_fdb_del(struct ndmsg *ndm, u16 vid); extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev, u16 mode); + struct net_device *dev, u16 mode, + u32 flags, u32 mask); #endif /* __LINUX_RTNETLINK_H */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index aa5cd2c53a56..61cb7e7cc3c7 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2687,12 +2687,22 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } +static int brport_nla_put_flag(struct sk_buff *skb, u32 flags, u32 mask, + unsigned int attrnum, unsigned int flag) +{ + if (mask & flag) + return nla_put_u8(skb, attrnum, !!(flags & flag)); + return 0; +} + int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev, u16 mode) + struct net_device *dev, u16 mode, + u32 flags, u32 mask) { struct nlmsghdr *nlh; struct ifinfomsg *ifm; struct nlattr *br_afspec; + struct nlattr *protinfo; u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; struct net_device *br_dev = netdev_master_upper_dev_get(dev); @@ -2731,6 +2741,33 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, } nla_nest_end(skb, br_afspec); + protinfo = nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED); + if (!protinfo) + goto nla_put_failure; + + if (brport_nla_put_flag(skb, flags, mask, + IFLA_BRPORT_MODE, BR_HAIRPIN_MODE) || + brport_nla_put_flag(skb, flags, mask, + IFLA_BRPORT_GUARD, BR_BPDU_GUARD) || + brport_nla_put_flag(skb, flags, mask, + IFLA_BRPORT_FAST_LEAVE, + BR_MULTICAST_FAST_LEAVE) || + brport_nla_put_flag(skb, flags, mask, + IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK) || + brport_nla_put_flag(skb, flags, mask, + IFLA_BRPORT_LEARNING, BR_LEARNING) || + brport_nla_put_flag(skb, flags, mask, + IFLA_BRPORT_LEARNING_SYNC, BR_LEARNING_SYNC) || + brport_nla_put_flag(skb, flags, mask, + IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD) || + brport_nla_put_flag(skb, flags, mask, + IFLA_BRPORT_PROXYARP, BR_PROXYARP)) { + nla_nest_cancel(skb, protinfo); + goto nla_put_failure; + } + + nla_nest_end(skb, protinfo); + return nlmsg_end(skb, nlh); nla_put_failure: nlmsg_cancel(skb, nlh); -- cgit v1.2.3 From 395eea6ccf2b253f81b4718ffbcae67d36fe2e69 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Wed, 3 Dec 2014 13:46:24 -0800 Subject: rtnetlink: delay RTM_DELLINK notification until after ndo_uninit() The commit 56bfa7ee7c ("unregister_netdevice : move RTM_DELLINK to until after ndo_uninit") tried to do this ealier but while doing so it created a problem. Unfortunately the delayed rtmsg_ifinfo() also delayed call to fill_info(). So this translated into asking driver to remove private state and then query it's private state. This could have catastropic consequences. This change breaks the rtmsg_ifinfo() into two parts - one takes the precise snapshot of the device by called fill_info() before calling the ndo_uninit() and the second part sends the notification using collected snapshot. It was brought to notice when last link is deleted from an ipvlan device when it has free-ed the port and the subsequent .fill_info() call is trying to get the info from the port. kernel: [ 255.139429] ------------[ cut here ]------------ kernel: [ 255.139439] WARNING: CPU: 12 PID: 11173 at net/core/rtnetlink.c:2238 rtmsg_ifinfo+0x100/0x110() kernel: [ 255.139493] Modules linked in: ipvlan bonding w1_therm ds2482 wire cdc_acm ehci_pci ehci_hcd i2c_dev i2c_i801 i2c_core msr cpuid bnx2x ptp pps_core mdio libcrc32c kernel: [ 255.139513] CPU: 12 PID: 11173 Comm: ip Not tainted 3.18.0-smp-DEV #167 kernel: [ 255.139514] Hardware name: Intel RML,PCH/Ibis_QC_18, BIOS 1.0.10 05/15/2012 kernel: [ 255.139515] 0000000000000009 ffff880851b6b828 ffffffff815d87f4 00000000000000e0 kernel: [ 255.139516] 0000000000000000 ffff880851b6b868 ffffffff8109c29c 0000000000000000 kernel: [ 255.139518] 00000000ffffffa6 00000000000000d0 ffffffff81aaf580 0000000000000011 kernel: [ 255.139520] Call Trace: kernel: [ 255.139527] [] dump_stack+0x46/0x58 kernel: [ 255.139531] [] warn_slowpath_common+0x8c/0xc0 kernel: [ 255.139540] [] warn_slowpath_null+0x1a/0x20 kernel: [ 255.139544] [] rtmsg_ifinfo+0x100/0x110 kernel: [ 255.139547] [] rollback_registered_many+0x1d5/0x2d0 kernel: [ 255.139549] [] unregister_netdevice_many+0x1f/0xb0 kernel: [ 255.139551] [] rtnl_dellink+0xbb/0x110 kernel: [ 255.139553] [] rtnetlink_rcv_msg+0xa0/0x240 kernel: [ 255.139557] [] ? rhashtable_lookup_compare+0x43/0x80 kernel: [ 255.139558] [] ? __rtnl_unlock+0x20/0x20 kernel: [ 255.139562] [] netlink_rcv_skb+0xb1/0xc0 kernel: [ 255.139563] [] rtnetlink_rcv+0x25/0x40 kernel: [ 255.139565] [] netlink_unicast+0x178/0x230 kernel: [ 255.139567] [] netlink_sendmsg+0x30f/0x420 kernel: [ 255.139571] [] sock_sendmsg+0x9c/0xd0 kernel: [ 255.139575] [] ? rw_copy_check_uvector+0x6f/0x130 kernel: [ 255.139577] [] ? copy_msghdr_from_user+0x139/0x1b0 kernel: [ 255.139578] [] ___sys_sendmsg+0x304/0x310 kernel: [ 255.139581] [] ? handle_mm_fault+0xca3/0xde0 kernel: [ 255.139585] [] ? destroy_inode+0x3c/0x70 kernel: [ 255.139589] [] ? __do_page_fault+0x20c/0x500 kernel: [ 255.139597] [] ? dput+0xb6/0x190 kernel: [ 255.139606] [] ? mntput+0x26/0x40 kernel: [ 255.139611] [] ? __fput+0x174/0x1e0 kernel: [ 255.139613] [] __sys_sendmsg+0x49/0x90 kernel: [ 255.139615] [] SyS_sendmsg+0x12/0x20 kernel: [ 255.139617] [] system_call_fastpath+0x12/0x17 kernel: [ 255.139619] ---[ end trace 5e6703e87d984f6b ]--- Signed-off-by: Mahesh Bandewar Reported-by: Toshiaki Makita Cc: Eric Dumazet Cc: Roopa Prabhu Cc: David S. Miller Acked-by: Eric Dumazet Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 5 +++++ net/core/dev.c | 12 +++++++++--- net/core/rtnetlink.c | 25 +++++++++++++++++++++---- 3 files changed, 35 insertions(+), 7 deletions(-) (limited to 'include/linux/rtnetlink.h') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 3b0419072f88..5db76a32fcab 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -17,6 +17,11 @@ extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, long expires, u32 error); void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change, gfp_t flags); +struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, + unsigned change, gfp_t flags); +void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, + gfp_t flags); + /* RTNL is used as a global lock for all changes to network configuration */ extern void rtnl_lock(void); diff --git a/net/core/dev.c b/net/core/dev.c index 0814a560e5f3..dd3bf582e6f0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5925,6 +5925,8 @@ static void rollback_registered_many(struct list_head *head) synchronize_net(); list_for_each_entry(dev, head, unreg_list) { + struct sk_buff *skb = NULL; + /* Shutdown queueing discipline. */ dev_shutdown(dev); @@ -5934,6 +5936,11 @@ static void rollback_registered_many(struct list_head *head) */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, + GFP_KERNEL); + /* * Flush the unicast and multicast chains */ @@ -5943,9 +5950,8 @@ static void rollback_registered_many(struct list_head *head) if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); - if (!dev->rtnl_link_ops || - dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); + if (skb) + rtmsg_ifinfo_send(skb, dev, GFP_KERNEL); /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev)); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 61cb7e7cc3c7..a9be2c161702 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2245,8 +2245,8 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, - gfp_t flags) +struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, + unsigned int change, gfp_t flags) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -2264,11 +2264,28 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, kfree_skb(skb); goto errout; } - rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags); - return; + return skb; errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_LINK, err); + return NULL; +} + +void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags) +{ + struct net *net = dev_net(dev); + + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, flags); +} + +void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, + gfp_t flags) +{ + struct sk_buff *skb; + + skb = rtmsg_ifinfo_build_skb(type, dev, change, flags); + if (skb) + rtmsg_ifinfo_send(skb, dev, flags); } EXPORT_SYMBOL(rtmsg_ifinfo); -- cgit v1.2.3